OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer

Code release for OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer (TIP2020) DOI

Changelog

• 2020/04/21 upload the code.

Dataset

CIFAR-100

Requirements

• python 3.6
• PyTorch 1.2.0
• torchvision

Training

• Download datasets
• Train: python OS-CNN.py or python CNN.py
• Description : PyTorch CIFAR-100 Training with OSNet or PyTorch CIFAR-100 Training with Vanilla Model.

Accuracy and Cross-entropy loss

Citation

If you find this paper useful in your research, please consider citing:

@ARTICLE{9088302,

  author={X. {Li} and D. {Chang} and Z. {Ma} and Z. {Tan} and J. {Xue} and J. {Cao} and J. {Yu} and J. {Guo}},
  journal={IEEE Transactions on Image Processing}, 
  title={OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer}, 
  year={2020},
  volume={},
  number={},
  pages={1-1},
}

Contact

Thanks for your attention! If you have any suggestion or question, you can leave a message here or contact us directly:

• mazhanyu@bupt.edu.cn
• xiaoxulilut@gmail.com
• changdongliang@bupt.edu.cn